WO2007109320A2 - Application de la technologie de détection d'événements anormaux à la transformation des polymères - Google Patents

Application de la technologie de détection d'événements anormaux à la transformation des polymères Download PDF

Info

Publication number
WO2007109320A2
WO2007109320A2 PCT/US2007/007019 US2007007019W WO2007109320A2 WO 2007109320 A2 WO2007109320 A2 WO 2007109320A2 US 2007007019 W US2007007019 W US 2007007019W WO 2007109320 A2 WO2007109320 A2 WO 2007109320A2
Authority
WO
WIPO (PCT)
Prior art keywords
model
models
variables
measurements
abnormal
Prior art date
Application number
PCT/US2007/007019
Other languages
English (en)
Other versions
WO2007109320A3 (fr
Inventor
Anh T. Nguyen
Kenneth F. Emigholz
Stephen S. Woo
Stephen D. Vercher
Steven M. Orsak
Perry Alagappan
Original Assignee
Exxonmobil Research And Engineering Company
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Exxonmobil Research And Engineering Company filed Critical Exxonmobil Research And Engineering Company
Priority to EP07753629A priority Critical patent/EP2013814A4/fr
Priority to JP2009501541A priority patent/JP2009536971A/ja
Priority to CA2646327A priority patent/CA2646327C/fr
Publication of WO2007109320A2 publication Critical patent/WO2007109320A2/fr
Publication of WO2007109320A3 publication Critical patent/WO2007109320A3/fr

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
    • G05B23/0254—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B17/00—Systems involving the use of models or simulators of said systems
    • G05B17/02—Systems involving the use of models or simulators of said systems electric

Definitions

  • the present invention relates to the operation of a Polymer Process with specific example applied to a Polypropylene Process (PP).
  • PP in this example comprises of nine operation areas - the catalyst preparation area (Cat Prep), reactors (RX), recycle gas compressors, recycle gas recovery system, the dryers, two granule areas and two extruders system.
  • the present invention relates to determining when the process is deviating from normal operation and automatic generation of notifications isolating the abnormal portion of the process.
  • Polypropylene process is one of the most important and widely used processes for polymerizing propylene to produce polypropylene. Polypropylene is then used as intermediate materials in producing plastic products such as milk bottles, soft drink bottles, hospital gowns, diaper linings etc.
  • the PP is a very complex and tightly integrated system comprising of the catalyst preparation unit, reactors, recycle gas compressors, recycle gas recovery system, the dryer, granule systems and two extruders.
  • Figure 23 shows a typical PP layout.
  • the PP process employs catalysts in the form of very fine particles mixed with cold oil and grease to form a very thick and paste — like mixture.
  • the thick and paste-like property of the catalyst mixture makes it difficult to pump catalysts into the reactors, thus makes the catalyst system prone to plugging problems.
  • RX 1 & RX 2 two large reactors
  • the monomers are in contact with the catalysts, a very exothermic reaction occurs and polymer granules are formed in the reactor slurry.
  • cooling water is continuously pumped around the reactor jackets to maintain the reactor temperature at a desired target.
  • the PP has two distinct reactor configuration modes - One configuration mode utilizes two reactors (RX 1 & 2) in series, while the other mode requires a third reactor (RX 3) in series with the first two reactors.
  • the polymer slurry exiting the reactors is pumped into the separators where un-reacted monomers are removed and sent to the monomer recovery system before recycling back to the reactors.
  • the polymer granules are fed into the dryer system where any last trace of monomers is removed, any trace of catalyst residues is steam stripped and the granules are dried off.
  • the dry polymer granules are sent to the granule system where they are blended with additives and sent to the two extruders for pelletization.
  • the polymer pellets are then sent the storage system or to the load out system.
  • the current commercial practice is to use advanced process control applications to automatically adjust the process in response to minor process disturbances, to rely on human process intervention for moderate to severe abnormal operations, and to use automatic emergency process shutdown systems for very severe abnormal operations.
  • the normal practice to notify the console operator of the start of an abnormal process operation is through process alarms. These alarms are triggered when key process measurements (temperatures, pressures, flows, levels and compositions) violate predefined static set of operating ranges. This notification technology is difficult to provide timely alarms while keeping low false positive rate when the key measurements are correlated for complicated processes such as PP.
  • the present invention is a method and system for detecting an abnormal event for the polymer process unit.
  • the polymer process is a polyolefin process.
  • the polyolefin process is a polyethylene or polypropylene process or a combination thereof. It utilizes the existing Abnormal Event Detection (AED) technology but with modifications to handle the complicated dynamic nature of the PP due to the frequent changes in operating conditions due to grade switches, and sometimes changes in the reactor configuration to produce different product grades. The modifications include the development of models for different product grades, the mechanism to detect the onset of product grade switching state, the notification suppression during the grade transitional duration, and the automatic switching of models presented to the operator based on changes in the operating modes, and reactor configurations.
  • AED Abnormal Event Detection
  • the automatic switching of the models is in-apparent to the operators as they still utilize the same operator interfaces.
  • the PP AED application includes a number of highly integrated dynamic process units. The method compares the current operation to various models of normal operation for the covered units. If the difference between the operation of the unit and the normal operation indicates an abnormal condition in a process unit, then the cause of the abnormal condition is determined and relevant information is presented efficiently to the operator to take corrective actions.
  • Figure 1 shows how the information in the online system flows through the various transformations, model calculations, fuzzy Petri nets and consolidation to arrive at a summary trend which indicates the normality/ abnormality of the process areas.
  • Figure 2 shows a valve flow plot to the operator as a simple x-y plot.
  • Figure 3 shows three-dimensional redundancy expressed as a PCA model.
  • Figure 4 shows a schematic diagram of a fuzzy network setup.
  • Figure 5 shows a schematic diagram of the overall process for developing an abnormal event application.
  • Figure 6 shows a schematic diagram of the anatomy of a process control cascade.
  • Figure 7 shows a schematic diagram of the anatomy of a multivariable constraint controller, MVCC.
  • Figure 8 shows a schematic diagram of the on-line inferential estimate of current quality.
  • Figure 9 shows the KPI analysis of historical data.
  • Figure 10 shows a diagram of signal to noise ratio.
  • Figure 11 shows how the process dynamics can disrupt the correlation between the current values of two measurements.
  • Figure 12 shows the probability distribution of process data.
  • Figure 13 shows illustration of the press statistic.
  • Figure 14 shows the two-dimensional energy balance model.
  • Figure 15 shows a typical stretch of Flow, Valve Position, and Delta Pressure data with the long period of constant operation.
  • Figure 16 shows a type 4 fuzzy discriminator.
  • Figure 17 shows a flow versus valve paraeto chart.
  • Figure 18 shows a schematic diagram of operator suppression logic.
  • Figure 19 shows a schematic diagram of event suppression logic.
  • Figure 20 shows the setting of the duration of event suppression.
  • Figure 21 shows the event suppression and the operator suppression disabling predefined sets of inputs in the PCA model.
  • Figure 22 shows how design objectives are expressed in the primary interfaces used by the operator
  • Figure 23 shows the simplified schematic layout of a PP
  • Figure 24 shows the operator display of all the problem monitors for the PP operation.
  • Figure 25 shows the fuzzy-logic based continuous abnormality indicator for the Catalyst Plugging problem in the Poly8 Operation Area.
  • Figure 26 shows AED alerts of the Catalyst Plugging Problem in both the Poly 8 Operation, and the Poly8 Cat Area abnormality monitors.
  • Figure 27 shows that complete drill down for the Catalyst Plugging problem in the Poly8 Operation Area along with the supporting evidences.
  • Figure 28 shows the drill down for the Catalyst Plugging problem in the Poly 8 Cat Area with location of problem area.
  • Figure 29 shows the fuzzy logic network for detection of the Catalyst Plugging problem in the Poly8 Cat Area.
  • Figure 30 shows Fuzzy Logic Network couple with rules developed for automatic switching of PCA models underlying Poly 8 Operation
  • Figure 31 shows the Fuzzy Logic Network developed for automatic detection of grade switches and for setting process transitional duration
  • Figure 32 shows A Pareto Chart displaying the residuals of the deviating sensors corresponding to the Catalyst Plugging Problem highlighted in Figure 27.
  • Figure 33 shows the multi-trends for the tags in Figure 32. It shows the tag values and also the model predictions.
  • Figure 34 shows the pareto chart ranking the deviating valve flow models
  • Figure 35 shows the X-Y plot for a valve flow model - valve opening versus the flow.
  • Figure 36 shows the drill down for the controller monitors and Sensor validation checks.
  • Figure 37 shows the fuzzy logic network for the controller monitors and Sensor validation checks.
  • Figure 38 shows the drill down for the heuristic models.
  • Figure 39 shows the fuzzy logic for the heuristic models
  • Figure 40 shows a Valve Flow Monitor Fuzzy Net.
  • Figure 41 shows an example of valve out of controllable range.
  • Figure 42 shows a standard statistical program, which plots the amount of variation modeled by each successive PC.
  • Figure 43 shows the Event Suppression display.
  • Figure 44 shows the AED Event Feedback Form.
  • the present invention is a method to provide early notification of abnormal conditions in sections of the PP to the operator using a modified Abnormal Event Detection (AED) technology.
  • the modifications include the development of different models for different product grades, and the automatic switching of models presented to the operator based on changes in the operating modes, and reactor configurations. The switching of the models is in-apparent to the operators as they still utilize the same operator interfaces.
  • the PP AED application includes a number of highly integrated dynamic process units. The method compares the current operation to various models of normal operation for the covered units. If the difference between the operation of the unit and the normal operation indicates an abnormal condition in a process unit, then the cause of the abnormal condition is determined and relevant information is presented efficiently to the operator to take corrective actions.
  • this method uses fuzzy logic to combine multiple supportive evidences of abnormalities that contribute to an operational problem and estimates its probability in real-time. This probability is presented as a continuous signal to the operator thus removing any chattering associated with the current single sensor alarming-based on/off methods.
  • the operator is provided with a set of tools that allow complete investigation and drill down to the root cause of a problem for focused action. This approach has been demonstrated to furnish the operator with advanced warning of the abnormal operation that can be minutes to hours earlier than the conventional alarm system. This early notification lets the operator make informed decision and take corrective action to avert any escalation or mishaps.
  • This method has been successfully applied to the PP.
  • Figure 27 shows the complete drill down for the Catalyst Plugging problem in the Poly8 Operation area (the details of the subproblems are described later).
  • the PP AED application uses diverse sources of specific operational knowledge to combine indications from Principal Component Analysis (PCA), correlation-based engineering models such as Valve Flow models (VFM), heuristic models (HM) or specific "operating rules-of-thumb" collected from experienced operators that are constructed in the fuzzy logic network, Controller Monitoring and Sensor Consistency Check (CM) to monitor relevant sensors through the use of fuzzy logic networks.
  • PCA Principal Component Analysis
  • VFM Valve Flow models
  • HM heuristic models
  • CM Controller Monitoring and Sensor Consistency Check
  • This fuzzy logic network aggregates the evidence and indicates the combined confidence level of a potential problem. Therefore, the network can detect a problem with higher confidence at its initial developing stages and provide crucial lead-time for the operator to take compensatory or corrective actions to avoid serious incidents. This is a key advantage over the present commercial practice of monitoring PP based on single sensor alarming from a DCS system.
  • the PP unit is divided into equipment groups (referred to as key functional sections or operational sections). These equipment groups may be different for different PP units depending on its design. The procedure for choosing equipment groups which include specific process units of the PP unit is described in Appendix 1.
  • the present invention divides the Polypropylene Unit (PP) operation into the following overall monitors
  • the overall monitors carry out "gross model checking" to detect any deviation in the overall operation and cover a large number of sensors.
  • the special concern monitors cover areas with potentially serious concerns and consist of focused models for early detection.
  • the application provides for several practical tools such as those dealing with suppression of notifications generated from normal/routine operational events and elimination of false positives due to special cause operations.
  • the operator user interface is a critical component of the system as it provides the operator with a bird's eye view of the process.
  • the display is intended to give the operator a quick overview of PP operations and indicate the probability of any developing abnormalities.
  • Figure 24 shows the operator interface for the system.
  • a detailed description on operator interface design considerations is provided in subsection rV "Operator Interaction & Interface Design” under section "Deploying PCA models and Simple Engineering Models for AED” in Appendix 1 section IV, under The interface consists of the abnormality monitors mentioned above. This was developed to represent the list of important abnormal indications in each operation area. Comparing model results with the state of key sensors generates abnormal indications. Fuzzy logic is used to aggregate abnormal indications to evaluate a single probability of a problem. Based on specific knowledge about the normal operation of each section, we developed a fuzzy logic network to take the input from sensors and model residuals to evaluate the probability of a problem.
  • Figure 25 shows the probability for the Catalyst Plugging problem in the Poly8 Cat area using the corresponding fuzzy logic network shown in Figure 29.
  • Figure 26 shows that the Catalyst Plugging Problem is seen in both the Poly 8 Operation and Poly ⁇ Cat Area abnormality monitors.
  • Figure 27 shows the complete drill down of the catalyst plugging problem in the Poly8 Operation Area.
  • Figure 28 shows the complete drill down of the catalyst plugging problem in the Poly8 Cat Area identifying the location of the plug.
  • Figure 29 shows the fuzzy logic network with the green nodes indicating the subproblems that combine together to determine the final certainty of the Catalyst Plugging Problem in the Poly ⁇ Cat Area.
  • the estimated probability of an abnormal condition is shown to the operating team in a continuous trend to indicate the condition's progression as shown in Figure 26.
  • This invention comprises five Principle Component Analysis (PCA) models to cover the areas of Cat. Prep., the Reactors including two Loop Reactors (RX 1 & 2) and a Gas Phase Reactor (RX 3), the Monomer Gas Recycle System, Recycle Gas Compressor, the dryers, the granule areas and two extruders system including Extruders 801 area, and Extrusion EX831 area.
  • PCA Principle Component Analysis
  • the fourth and fifth PCAjmodels represent the two extrusion areas labeled as "EX801 Operation", and "EX831 Operation”.
  • EX801 Operation the two extrusion areas labeled as "EX801 Operation”
  • EX831 Operation the two extrusion areas labeled as "EX801 Operation”
  • special concern monitors intended to watch conditions that could escalate into serious events. The objective is to detect the problems early on so that the operator has sufficient lead time to act.
  • the existing AED notification - suppression mechanism could not handle the grade switches, and therefore modifications were made.
  • the modifications include mechanism to detect the onset of a grade switch and set a grade -switch state. The grade switch state is then latched on for a certain period of time to depict a process transitional duration.
  • the notifications are suppressed using the existing mechanism to avoid flooding operators with nuisance alerts, as they are already aware of the condition changes, and are already keeping a close watch of the PP.
  • AED continues to update PCA model parameters, and once the PP reaches its new steady state, AED resumes its notification.
  • Figure 31 shows the added fuzzy network logics for automatic detection of grade switches and for setting the transitional duration.
  • FIG. 32 demonstrates this functionality through a list of sensors organized in a pareto- chart. Upon clicking on an individual bar, a custom plot showing the tag trend versus model prediction for the sensor is created. The operator can also look at trends of problem sensors together using the "multi-trend view”. For instance, Figure 33 shows the trends of the value and model predictions of the sensors in the Pareto chart of Figure 32.
  • Figure 34 shows the same concept, this time applied to the ranking of valve-flow models (VFM) based on the normalized- projection-deviation error. Clicking on the bar in this case, generates an X-Y scatter plot that shows the current operation point in the context of the bounds of normal operation ( Figure 35).
  • VFM valve-flow models
  • the PCA models provide model predictions of the 450+ sensors covered in the models. 5. The abnormal deviations of these sensors are summarized by the 5 alerts based on the Sum of Square Error of the 5 PCA models
  • valve- flow models provide a powerful way to monitor control loops, which effect control actions and thus can be the source or by affected by upsets.
  • the controller monitors and the sensor checks add enhanced focused and early detection capability for key process variables.
  • the application has PCA models, engineering models and heuristics to detect abnormal operation in a PP.
  • the first steps involve analyzing the concerned unit for historical operational problems. This problem identification step is important to define the scope of the application.
  • the first step in the application development is to identify a significant problem, which will benefit process operations.
  • the abnormal event detection application in general can be applied to two different classes of problem.
  • the first is a generic abnormal event application that monitors an entire process area looking for any abnormal event. This type will use several hundred measurements, but does not require a historical record of any specific abnormal operations.
  • the application will only detect and link an abnormal event to a portion (tags) of the process. Diagnosis of the problem requires the skill of the operator or engineer.
  • the second type is focused on a specific abnormal operation.
  • This type will provide a specific diagnosis once the abnormality is detected. It typically involves only a small number of measurements (5 -20), but requires a historical data record of the event.
  • These models can be PCA based or simple engineering correlation such as the Valve Flow (VF) models monitoring the main process flow valves for broken correlation or out-of-range operation that are constructed based on historical data of sensors around the flow control valve such as upstream/downstream pressure, flow measurement and valve output; the Heuristic Models (HM) are specific "operating rules-of-thumb" collected from experienced operators and are constructed in the fuzzy logic network to identify those circumstances that violate these rules-of-thumb; the Controller Monitoring (CM) and Sensor Check (SC) monitor the performance of the controller or sensor to detect a frozen instrument, a controller malfunction, or an instrument that has a highly variant reading.
  • VF Valve Flow
  • HM Heuristic Models
  • CM Controller Monitoring
  • SC Sensor Check
  • This invention uses the above models in order to provide extensive coverage. The operator or the engineer would then rely on their process knowledge / expertise to accurately diagnose the cause. Typically most of the events seem to be primarily the result of problems with the instruments and valves. [0069] The following problem characteristics should be considered when selecting an abnormal event detection problem: Infrequent abnormalities (every 3 - 4 months) may not justify the effort to create an abnormal event detector. Also, when a particular abnormality occurs only every 3 or 4 months, an individual operator may go for years without seeing the event. As a consequence, he would not know what to do once the event finally occurs. Therefore the problem identification should be broad enough that the operator would be regularly interacting with the application.
  • the application should cover a large enough portion of the process to "see" abnormal events on a regular basis (e.g. more than 5 times each week).
  • PCA Principal Components
  • Each principal component captures a unique portion of the process variability caused by these different independent influences on the process.
  • the principal components are extracted in the order of decreasing process variation.
  • Each subsequent principal component captures a smaller portion of the total process variability.
  • the major principal components should represent significant underlying sources of process variation.
  • the first principal component often represents the effect of feed rate changes since this is usually the largest single source of process changes.
  • PCA Principal Component Analysis
  • PCA models developed for PP There are five PCA models developed for PP.
  • the two PCA models underlying the Poly8 Operation to cover the two reactor configuration modes are Poly8_TCR and Poly8_ICP. These two PCA models include sensors in the Catalyst Preparation, the Reactors, the Monomer Gas Recycle system and the Recycle Gas Compressor because there is significant interaction between these systems.
  • the Poly8_TCR PCA model started with an initial set of 321 tags, which was then refined to 155 tags.
  • the Poly8_ICP PCA model started with an initial set of 414 tags, which was then refined to 200 tags.
  • the Dryer ⁇ model started with an initial set of 76 tags in the dryers, and the granule areas, which was then refined to 37 tags.
  • the EX801 model narrowed down from 43 to 25 tags to cover the extrusion 1 area.
  • the EX831 model narrowed down from 43 to 25 tags to cover the extrusion 2 area.
  • the details of the Poly ⁇ JTCR PCA model is shown in Appendix 2A, the Poly8_ICP PCA model in Appendix 2B, the Dryer8 PCA model in Appendix 2C, the EX801 PCA model in Appendix 2D, the EX831PCA model in Appendix 2E. This allows extensive coverage of the overall PP operation and early alerts.
  • the PCA model development comprises of the following steps:
  • the historical data spanned 1.5 years of operation to cover the production of all product grades as well as both summer and winter seasons. With one-minute averaged data the number of time points turn out to be arou ⁇ d 700,000+ for each tag.
  • the tag list was divided up into two sub-sets of tags for data collection and analysis.
  • the historical data is divided into periods with known abnormal operations and periods with no identified abnormal operations.
  • the data with no identified abnormal operations will be the preliminary training data set.
  • operating logs were studied to determine the time periods when each product grade is produced.
  • the historical data set is then divided up and saved by the grade families.
  • Each grade family data set is then analyzed for exclusion of periods with known abnormal operations and periods with no identified abnormal operations.
  • the model development strategy is to start with a very rough model (the consequence of a questionable training data set) then use the model to gather a high quality training data set. This data is then used to improve the model, which is then used to continue to gather better quality training data. This process is repeated until the model is satisfactory.
  • the initial model needs to be enhanced by creating a new training data set. This is done by using the model to monitor the process. Once the model indicates a potential abnormal situation, the engineer should investigate and classify the process situation. The engineer will find three different situation, either some special process operation is occurring, an actual abnormal situation is occurring, or the process is normal and it is a false indication.
  • the developer or site engineer may determine that it is necessary to improve one of the models. Either the process conditions have changed or the model is providing a false indication. In this event, the training data set could be augmented with additional process data and improved model coefficients could be obtained. The trigger points can be recalculated using the same rules of thumb mentioned previously.
  • the engineering models comprise of correlation-based models focused on specific detection of abnormal conditions.
  • the detailed description of building engineering models can be found under "Simple Engineering Models for AED" section in Appendix 1.
  • the engineering model requirements for the PP application were determined by performing an engineering evaluation of historical process data and interviews with console operators and equipment specialists.
  • the engineering evaluation included areas of critical concern and worst case scenarios for PP operation.
  • the following engineering models were developed for the PP AED application:
  • the Flow- Valve position consistency monitor was derived from a comparison of the measured flow (compensated for the pressure drop across the valve) with a model estimate of the flow. These are powerful checks as the condition of the control loops are being directly monitored in the process.
  • the model estimate of the flow is obtained from historical data by fitting coefficients to the valve curve equation (assumed to be either linear or parabolic).
  • 20 flow/valve position consistency models were developed. An example is shown in Figure 35 for the Monomer Flow Valve.
  • Several models were also developed for the flow control loops which historically exhibited unreliable performance. The details of the valve flow models are given in Appendix 3 A.
  • Figure 41 shows both the components of the fuzzy network and an example of value-exceedance is shown in Figure 40
  • a time-varying drift term was added to the model estimate to compensate for long term sensor drift.
  • the operator can also request a reset of the drift term after a sensor recalibration or when a manual bypass valve has been changed. This modification to the flow estimator significantly improved the robustness for implementation within an online detection algorithm.
  • the controller monitors (CM) and sensor checks (SC) were derived by analyzing the historical data and applying simple engineering calculations.
  • the model for the CM was derived from calculation of the standard of deviation (SD) to detect a frozen instrument in the case the measurement experiences very low SD or a highly variant instrument when the measurement experiences high SD.
  • Other calculations for CM include the accumulation of the length of time during which the measurement is not meeting and not criss-crossing the setpoint, and also the accumulation of the deviation between the measurement and the setpoint to detect the controller malfunction.
  • the model for the SC was obtained by analyzing the historical data for the relationship between measurements. These are powerful checks as the condition of the controllers or the sensors are being directly monitored and compared to the models. The details of the meas ⁇ rement correlation are given in Appendix 3 B.
  • the abnormal monitor with drill down to the subproblem is shown in Figure 36.
  • the components of the fuzzy network are shown in Figure 37.
  • HM heuristic models
  • the heuristic models are specific "operating rules-of-thumb" collected from experienced operators. These models identify those circumstances that violate these rules-of-thumb.
  • An example is the monitoring of 801 granule area process variables to detect potential line plugging problems with the details given in Appendix 3 C.
  • the abnormal monitor with drill down to the subproblem is shown in Figure 38.
  • the components of the fuzzy network are shown in Figure 39.
  • AED is fairly straightforward.
  • the trigger points for notification were initially derived from the standard deviation of the model residual.
  • the trigger points for notification were determined from the analysis of historical data in combination with console operator input.
  • known AED indications were reviewed with the operator to ensure that the trigger points were appropriate and modified as necessary. Section "Deploying PCA Models and Simple Engineering Models for AED" in Appendix 1 describes details of engineering model deployment.
  • valve/flow diagnostics could provide the operator with redundant notification. Model suppression was applied to the valve / flow diagnostics to provide the operator with a single alert to a problem with a valve/flow pair.
  • a tag If a tag has been removed from service for an extended period, it can also be disabled.
  • product grade switches are done very frequently. There are grade switches within a product grade family (called flying grade-switch) that do not require changes in reactor configuration. In this case, operators can make large setpoint changes to some key product-quality controllers to steer the PP to a new operation state. During the transitional state, some sensors will experience high residuals and therefore depict abnormal conditions. Modifications were made to the existing AED notification - suppression mechanism to handle the grade switches. The modifications include mechanism to detect the onset of a grade switch and set a grade -switch state. The grade switch state is then latched on for a certain period of time to depict a process transitional duration.
  • FIG. 31 shows the fuzzy logic network for automatic detection of grade switches and for setting the transitional duration. There are also product grade switches requiring changes in reactor configuration (from two reactor mode to three reactor mode and vice versa). This modification of the AED notification suppression also handles the suppression for this case.
  • the list of events currently suppressed is shown in Figure 43.
  • the alarm system will identify the problem as quickly as an abnormal event detection application.
  • the sequence of events e.g. the order in which measurements become unusual
  • abnormal event detection applications can give the operator advanced warning when abnormal events develop slowly (longer than 15 minutes). These applications are sensitive to a change in the pattern of the process data rather than requiring a large excursion by a single variable. Consequently alarms can be avoided. If the alarm system has been configured to alert the operator when the process moves away from a small operating region (not true safety alarms), this application may be able to replace these alarms.
  • the AED system In addition to just detecting the presence of an abnormal event the AED system also isolates the deviant sensors for the operator to investigate the event. This is a crucial advantage considering that modern plants have thousands of sensors and it is humanly infeasible to monitor them all online. The AED system can thus be thought of as another powerful addition to the operator toolkit to deal with abnormal situations efficiently and effectively.
  • a methodology and system has been developed to create and to deploy on-line, sets of models, which are used to detect abnormal operations and help the operator isolate the location of the root cause.
  • the models employ principle component analysis (PCA).
  • PCA principle component analysis
  • These sets of models are composed of both simple models that represent known engineering relationships and principal component analysis (PCA) models that represent normal data patterns that exist within historical databases. The results from these many model calculations are combined into a small number of summary time trends that allow the process operator to easily monitor whether the process is entering an abnormal operation.
  • Figure 1 shows how the information in the online system flows through the various transformations, model calculations, fuzzy Petri nets and consolidations to arrive at a summary trend which indicates the normality / abnormality of the process areas.
  • the heart of this system is the various models used to monitor the normality of the process operations.
  • the PCA models described in this invention are intended to broadly monitor continuous refining and chemical processes and to rapidly detect developing equipment and process problems.
  • the intent is to provide blanket monitoring of all the process equipment and process operations under the span of responsibility of a particular console operator post. This can involve many major refining or chemical process operating units (e.g. distillation towers, reactors, compressors, heat exchange trains, etc.) which have hundreds to thousands of process measurements.
  • the monitoring is designed to detect problems which develop on a minutes to hours timescale, as opposed to long term performance degradation.
  • the process and equipment problems do not need to be specified beforehand. This is in contrast to the use of PCA models cited in the literature which are structured to detect a specific important process problem and to cover a much smaller portion of the process operations.
  • the method for PCA model development and deployment includes a number of novel extensions required for their application to continuous refining and chemical processes including:
  • the process is stationary — its mean and variance are constant over time.
  • the covariance matrix of the process variables is not degenerate (i.e. positive semi-definite).
  • redundancy checks are simple 2x2 checks, e.g.
  • Multidimensional checks are represented with "PCA like" models.
  • Figure 3 there are three independent and redundant measures, Xl, X2, and X3. Whenever X3 changes by one, Xl changes by a 13 and X2 changes by a 23 .
  • This set of relationships is expressed as a PCA model with a single principle component direction, P.
  • This type of model is presented to the operator in a manner similar to the broad PCA models.
  • the gray area shows the area of normal operations.
  • the principle component loadings of P are directly calculated from the engineering equations, not in the traditional manner of determining P from the direction of greatest variability.
  • Each redundancy check is also converted to a continuous normal - abnormal indication using fuzzy nets.
  • fuzzy nets There are two different indices used for these models to indicate abnormality; deviation from the model and deviation outside the operating range (shown on Figure 3). These deviations are equivalent to the sum of the square of the error and the Hotelling T square indices for PCA models. For checks with dimension greater than two, it is possible to identify which input has a problem. In Figure 3, since the X3-X2 relationship is still within the normal envelope, the problem is with input Xl.
  • Each deviation measure is converted by the fuzzy Petri net into a zero to one scale that will continuously indicate the range from normal operation (value of zero) to abnormal operation (value of one).
  • the overall process for developing an abnormal event application is shown in Figure 5.
  • the basic development strategy is iterative where the developer starts with a rough model, then successively improves that model's capability based on observing how well the model represents the actual process operations during both no ⁇ nal operations and abnormal operations.
  • the models are then restructured and retrained based on these observations.
  • Equipment groups are defined by including all the major material and energy integrations and quick recycles in the same equipment group. If the process uses a multivariable constraint controller, the controller model will explicitly identify the interaction points among the process units. Otherwise the interactions need to be identified through an engineering analysis of the process. [00138] Process groups should be divided at a point where there is a minimal interaction between the process equipment groups. The most obvious dividing point occurs when the only interaction comes through a single pipe containing the feed to the next downstream unit. In this case the temperature, pressure, flow, and composition of the feed are the primary influences on the downstream equipment group and the pressure in the immediate downstream unit is the primary influence on the upstream equipment group. These primary influence measurements should be included in both the upstream and downstream equipment group PCA models.
  • [00139] Include the influence of the process control applications between upstream and downstream equipment groups.
  • the process control applications provide additional influence paths between upstream and downstream equipment groups. Both feedforward and feedback paths can exist. Where such paths exist the measurements which drive these paths need to be included in both equipment groups. Analysis of the process control applications will indicate the major interactions among the process units.
  • Process operating modes are defined as specific time periods where the process behavior is significantly different. Examples of these are production of different grades of product (e.g. polymer production), significant process transitions (e.g. startups, shutdowns, feedstock switches), processing of dramatically different feedstock (e.g. cracking naphtha rather than ethane in olefins production), or different configurations of the process equipment (different sets of process units running).
  • grades of product e.g. polymer production
  • significant process transitions e.g. startups, shutdowns, feedstock switches
  • processing of dramatically different feedstock e.g. cracking naphtha rather than ethane in olefins production
  • different configurations of the process equipment different sets of process units running.
  • Inferential measurements are usually ⁇ developed using partial least squares, PLS, models which are very close relatives to PCA abnormal event models. Other common alternatives for developing inferential measurements include Neural Nets and linear regression models. If the data exists which can be used to reliably measure the approach to the problem condition (e.g. tower flooding using delta pressure), this can then be used to not only detect when the condition exists but also as the base for a control application to prevent the condition from occurring. This is the third best approach.
  • the signal to noise ratio is a measure of the information content in the input signal.
  • the signal to noise ratio is calculated as follows:
  • the raw signal is filtered using an exponential filter with an approximate dynamic time constant equivalent to that of the process.
  • this time constant is usually in the range of 30 minutes to 2 hours.
  • Other low pass filters can be used as well.
  • the exponential filter the equations are:
  • a residual signal is created by subtracting the filtered signal from the raw signal
  • the signal to noise ratio is the ratio of the standard deviation of the filtered signal divided by the standard deviation of the residual signal
  • the data set used to calculate the S/N should exclude any long periods of steady-state operation since that will cause the estimate for the noise content to be excessively large.
  • the cross correlation is a measure of the information redundancy the input data set.
  • the cross correlation between any two signals is calculated as:
  • Si k N* ⁇ (X L *X k ) - ( ⁇ Xr> * ( ⁇ Xi ⁇ Equation 5
  • the first circumstance occurs when there is no significant correlation between a particular input and the rest of the input data set. For each input, there must be at least one other input in the data set with a significant correlation coefficient, such as 0.4.
  • the second circumstance occurs when the same input information has been (accidentally) included twice, often through some calculation, which has a different identifier. Any input pairs that exhibit correlation coefficients near one (for example above 0.95) need individual examination to determine whether both inputs should be included in the model. If the inputs are physically independent but logically redundant (i.e., two independent thermocouples are independently measuring the same process temperature) then both these inputs should be included in the model.
  • the process control system could be configured on an individual measurement basis to either assign a special code to the value for that measurement to indicate that the measurement is a Bad Value, or to maintain the last good value of the measurement. These values will then propagate throughout any calculations performed on the process control system. When the "last good value” option has been configured, this can lead to erroneous calculations that are difficult to detect and exclude. Typically when the "Bad Value” code is propagated through the system, all calculations which depend on the bad measurement will be flagged bad as well.
  • Constrained variables are ones where the measurement is at some limit, and this measurement matches an actual process condition (as opposed to where the value has defaulted to the maximum or minimum limit of the transmitter range - covered in the Bad Value section). This process situation can occur for several reasons:
  • the process control system is designed to drive the process against process operating limits, for example product spec limits. These constraints typically fall into two categories: - those, which are occasionally saturated and those, which are normally saturated. Those inputs, which are normally saturated, should be excluded from the model. Those inputs, which are only occasionally saturated (for example less than 10% of the time) can be included in the model however, they should be scaled based on the time periods when they are not saturated.
  • FIG. 6 shows a typical "cascade" process control application, which is a very common control structure for refining and chemical processes. Although there are many potential model inputs from such an application, the only ones that are candidates for the model are the raw process measurements (the “PVs” in this figure ) and the final output to the field valve.
  • the PV of the ultimate primary of the cascade control structure is a poor candidate for inclusion in the model.
  • This measurement usually has very limited movement since the objective of the control structure is to keep this measurement at the setpoint.
  • There can be movement in the PV of the ultimate primary if its setpoint is changed but this usually is infrequent.
  • the data patterns from occasional primary setpoint moves will usually not have sufficient power in the training dataset for the model to characterize the data pattern.
  • this measurement should be scaled based on those brief time periods during which the operator has changed the setpoint and until the process has moved close to the vale of the new setpoint (for example within 95% of the new setpoint change thus if the setpoint change is from 10 to 11, when the PV reaches 10.95)
  • thermocouples located near a temperature measurement used as a PV for an Ultimate Primary. These redundant measurements should be treated in the identical manner that is chosen for the PV of the Ultimate Primary.
  • Cascade structures can have setpoint limits on each secondary and can have output limits on the signal to the field control valve. It is important to check the status of these potentially constrained operations to see whether the measurement associated with a setpoint has been operated in a constrained manner or whether the signal to the field valve has been constrained. Date during these constrained operations should not be used.
  • FIG. 7 shows a typical MVCC process control application, which is a very common control structure for refining and chemical processes.
  • An MVCC uses a dynamic mathematical model to predict how changes in manipulated variables, MVs, (usually valve positions or setpoints of regulatory control loops) will change control variables, CVs (the dependent temperatures, pressures, compositions and flows which measure the process state).
  • An MVCC attempts to push the process operation against operating limits. These limits can be either MV limits or CV limits and are determined by an external optimizer. The number of limits that the process operates against will be equal to the number of MVs the controller is allowed to manipulate minus the number of material balances controlled. So if an MVCC has 12 MVs, 30 CVs and 2 levels then the process will be operated against 10 limits.
  • An MVCC will also predict the effect of measured load disturbances on the process and compensate for these load disturbances (known as feedforward variables, FF).
  • Whether or not a raw MV or CV is a good candidate for inclusion in the PCA model depends on the percentage of time that MV or CV is held against its operating limit by the MVCC. As discussed in the Constrained Variables section, raw variables that are constrained more than 10% of the time are poor candidates for inclusion in the PCA model. Normally unconstrained variables should be handled per the Constrained Variables section discussion.
  • an unconstrained MV is a setpoint to a regulatory control loop
  • the setpoint should not be included; instead the measurement of that regulatory control loop should be included.
  • the signal to the field valve from that regulatory control loop should also be included.
  • an unconstrained MV is a signal to a field valve position, then it should be included in the model.
  • the process control system databases can have a significant redundancy among the candidate inputs into the PCA model.
  • One type of redundancy is “physical redundancy”, where there are multiple sensors (such as thermocouples) located in close physical proximity to each other within the process equipment.
  • the other type of redundancy is “calculational redundancy”, where raw sensors are mathematically combined into new variables (e.g. pressure compensated temperatures or mass flows calculated from volumetric flow measurements).
  • both the raw measurement and an input which is calculated from that measurement should not be included in the model.
  • the general preference is to include the version of the measurement that the process operator is most familiar with.
  • the exception to this rule is when the raw inputs must be mathematically transformed in order to improve the correlation structure of the data for the model. In that case the transformed variable should be included in the model but not the raw measurement.
  • Physical redundancy is very important for providing cross validation information in the model.
  • raw measurements which are physically redundant, should be included in the model.
  • these measurements must be specially scaled so as to prevent them from overwhelming the selection of principle components (see the section on variable scaling).
  • a common process example occurs from the large number of thermocouples that are placed in reactors to catch reactor runaways.
  • Span the normal operating range Datasets, which span small parts of the operating range, are composed mostly of noise. The range of the data compared to the range of the data during steady state operations is a good indication of the quality of the information in the dataset.
  • History should be as similar as possible to the data used in the online system:
  • the online system will be providing spot values at a frequency fast enough to detect the abnormal event. For continuous refining and chemical operations this sampling frequency will be around one minute.
  • the training data should be as equivalent to one- minute spot values as possible.
  • the strategy for data collection is to start with a long operating history (usually in the range of 9 months to 18 months), then try to remove those time periods with obvious or documented abnormal events. By using such a long time period,
  • the training data set needs to have examples of all the normal operating modes, normal operating changes and changes and normal minor disturbances that the process experiences. This is accomplished by using data from over a long period of process operations (e.g. 9 - 18 months). In particular, the differences among seasonal operations (spring, summer, fall and winter) can be very significant with refinery and chemical processes.
  • Old data that no longer properly represents the current process operations should be removed from the training data set. After a major process modification, the training data and PCA model may need to be rebuilt from scratch. If a particular type of operation is no longer being done, all data from that operation should be removed from the training data set.
  • Operating logs should be used to identify when the process was run under different operating modes. These different modes may require separate models. Where the model is intended to cover several operating modes, the number of samples in the training dataset from each operating model should be approximately equivalent.
  • the developer should gather several months of process data using the site's process historian, preferably getting one minute spot values. If this is not available, the highest resolution data, with the least amount of averaging should be used.
  • the model development strategy is to start with an initial "rough" model (the consequence of a questionable training data set) then use the model to trigger the gathering of a high quality training data set.
  • annotations and data will be gathered on normal operations, special operations, and abnormal operations. Anytime the model flags an abnormal operation or an abnormal event is missed by the model, the cause and duration of the event is annotated. In this way feedback on the model's ability to monitor the process operation can be incorporated in the training data.
  • This data is then used to improve the model, which is then used to continue to gather better quality training data. This process is repeated until the model is satisfactory.
  • the historical data is divided into periods with known abnormal operations and periods with no identified abnormal operations.
  • the data with no identified abnormal operations will be the training data set.
  • the training data set should now be run through this preliminary model to identify time periods where the data does not match the model. These time periods should be examined to see whether an abnormal event was occurring at the time. If this is judged to be the case, then these time periods should also be flagged as times with known abnormal events occurring. These time periods should be excluded from the training data set and the model rebuilt with the modified data.
  • KPIs Key performance indicators
  • Such measurements as feed rates, product rates, product quality are common key performance indicators.
  • Each process operation may have additional KPIs that are specific to the unit. Careful examination of this limited set of measurements will usually give a clear indication of periods of abnormal operations.
  • Figure 9 shows a histogram of a KPI. Since the operating goal for this KPI is to maximize it, the operating periods where this KPI is low are likely abnormal operations. Process qualities are often the easiest KPIs to analyze since the optimum operation is against a specification limit and they are less sensitive to normal feed rate variations.
  • Noise we are referring to the high frequency content of the measurement signal which does not contain useful information about the process. Noise can be caused by specific process conditions such as two-phase flow across an orifice plate or turbulence in the level. Noise can be caused by electrical inductance. However, significant process variability, perhaps caused by process disturbances is useful information and should not be filtered out.
  • the amount of noise in the signal can be quantified by a measure known as the signal to noise ratio (see Figure 10). This is defined as the ratio of the amount of signal variability due to process variation to the amount of signal variability due to high frequency noise. A value below four is a typical value for indicating that the signal has substantial noise, and can harm the model's effectiveness.
  • the exponentially correlated continuous noise can be removed with a traditional low pass filter such as an exponential filter.
  • the equations for the exponential filter are:
  • Y n is the current filtered value
  • T s is the sample time of the measurement
  • T f is the filter time constant
  • Figure 11 shows how the process dynamics can disrupt the correlation between the current values of two measurements.
  • one value is constantly changing while the other is not, so there is no correlation between the current values during the transition.
  • these two measurements can be brought back into time synchronization by transforming the leading variable using a dynamic transfer function.
  • a first order with deadtime dynamic model shown in Equation 9 in the Laplace transform format
  • V(s) e " ⁇ S Y(s) Equation 9
  • the process measurements are transformed to deviation variables: deviation from a moving average operating point. This transformation to remove the average operating point is required when creating PCA models for abnormal event detection. This is done by subtracting the exponentially filtered value (see Equations 8 and 9 for exponential filter equations) of a measurement from its raw value and using this difference in the model.
  • X 1 X - Xfii tOTd Equation 10
  • the time constant for the exponential filter should be about the same size as the major time constant of the process. Often a time constant of around 40 minutes will be adequate. The consequence of this transformation is that the inputs to the PCA model are a measurement of the recent change of the process from the moving average operating point.
  • the data In order to accurately perform this transform, the data should be gathered at the sample frequency that matches the on-line system, often every minute or faster. This will result in collecting 525,600 samples for each measurement to cover one year of operating data. Once this transformation has been calculated, the dataset is resampled to get down to a more manageable number of samples, typically in the range of 30,000 to 50,000 samples.
  • the scaling should be based on the degree of variability that occurs during normal process disturbances or during operating point changes not on the degree of variability that occurs during continuous steady state operations.
  • the scaling factor there are two different ways of determining the scaling factor.
  • First is to identify time periods where the process was not running at steady state, but was also not experiencing a significant abnormal event.
  • a limited number of measurements act as the key indicators of steady state operations. These are typically the process key performance indicators and usually include the process feed rate, the product production rates and the product quality. These key measures are used to segment the operations into periods of normal steady state operations, normally disturbed operations, and abnormal operations. The standard deviation from the time periods of normally disturbed operations provides a good scaling factor for most of the measurements.
  • An alternative approach to explicitly calculating the scaling based on disturbed operations is to use the entire training data set as follows.
  • the scaling factor can be approximated by looking at the data distribuion outside of 3 standard deviations from the mean. For example, 99.7% of the data should lie, within 3 standard deviations of the mean and that 99.99% of the data should lie, within 4 standard deviations of the mean.
  • the span of data values between 99.7% and 99.99% from the mean can act as an approximation for the standard deviation of the "disturbed" data in the data set. See Figure 12.
  • PCA transforms the actual process variables into a set of independent variables called Principal Components, PC, which are linear combinations of the original variables (Equation 13).
  • the process will have a number of degrees of freedom, which represent the specific independent effects that influence the process. These different independent effects show up in the process data as process variation.
  • Process variation can be due to intentional changes, such as feed rate changes, or unintentional disturbances, such as ambient temperature variation.
  • Each principal component models a part of the process variability caused by these different independent influences on the process.
  • the principal components are extracted in the direction of decreasing variation in the data set, with each subsequent principal component modeling less and less of the process variability.
  • Significant principal components represent a significant source of process variation, for example the first principal component usually represents the effect of feed rate changes since this is usually the source of the largest process changes. At some point, the developer must decide when the process variation modeled by the principal components no longer represents an independent source of process variation.
  • the engineering approach to selecting the correct number of principal components is to stop when the groups of variables, which are the primary contributors to the principal component no longer make engineering sense.
  • the primary cause of the process variation modeled by a PC is identified by looking at the coefficients, Aj 3n , of the original variables (which are called loadings). Those coefficients, which are relatively large in magnitude, are the major contributors to a particular PC.
  • Aj 3n the coefficients, which are relatively large in magnitude, are the major contributors to a particular PC.
  • Someone with a good understanding of the process should be able to look at the group of variables, which are the major contributors to a PC and assign a name (e.g. feed rate effect) to that PC.
  • the coefficients become more equal in size.
  • the variation being modeled by a particular PC is primarily noise.
  • the process data will not have a gaussian or normal distribution. Consequently, the standard statistical method of setting the trigger for detecting an abnormal event at 3 standard deviations of the error residual should not be used. Instead the trigger point needs to be set empirically based on experience with using the model.
  • the trigger level should be set so that abnormal events would be signaled at a rate acceptable to the site engineer, typically 5 or 6 times each day. This can be determined by looking at the SPE x statistic for the training data set (this is also referred to as the Q statistic or the DMOD x statistic). This level is set so that real abnormal events will not get missed but false alarms will not overwhelm the site engineer.
  • the initial model needs to be enhanced by creating a new training data set. This is done by using the model to monitor the process. Once the model indicates a potential abnormal situation, the engineer should investigate and classify the process situation. The engineer will find three different situations, either some special process operation is occurring, an actual abnormal situation is occurring, or the process is normal and it is a false indication.
  • the new training data set is made up of data from special operations and normal operations. The same analyses as were done to create the initial model need to be performed on the data, and the model re-calculated. With this new model the trigger lever will still be set empirically, but now with better annotated data, this trigger point can be tuned so as to only give an indication when a true abnormal event has occurred.
  • N - convergence factor ( e.g. .0001 )
  • the "filtered bias” term updates continuously to account for persistent unmeasured process changes that bias the engineering redundancy model.
  • the convergence factor, "N" is set to eliminate any persistent change after a user specified time period, usually on the time scale of days.
  • the "normal operating range” and the "normal model deviation” are determined from the historical data for the engineering redundancy model. In most cases the max error value is a single value; however this can also be a vector of values that is dependent on the x axis location.
  • a particularly valuable engineering redundancy model is the flow versus valve position model. This model is graphically shown in Figure 2. The particular form of this model is:
  • Delta_Pressure ref e r ence '• average Delta Pressure during normal operation a model parameter fitted to historical data
  • the objectives of this model are to:
  • Figure 15 shows a typical stretch of Flow, Valve Position, and Delta Pressure data with the long periods of constant operation. The first step is to isolate the brief time periods where there is some significant variation in the operation, as shown. This should be then mixed with periods of normal operation taken from various periods in history.
  • the valve characteristic curve can be either fit with a linear valve curve, with a quadratic valve curve or with a piecewise linear function.
  • the piecewise linear function is the most flexible and will fit any form of valve characteristic curve.
  • the "normal operating range” index is the valve position distance from the normal region. It typically represents the operating region of the valve where a change in valve position will result in little or no change in the flow v through the valve.
  • a common way of grouping Flow / Valve models which is favored by the operators is to put all of these models into a single fuzzy network so that the trend indicator will tell them that all of their critical flow controllers are working.
  • the model indications into the fuzzy network ( Figure 4) will contain the "normal operating range” and the "normal model deviation” indication for each of the flow/valve models.
  • the trend will contain the discriminator result from the worst model indication.
  • a common equipment type is grouped together, another operator favored way to look at this group is through a Pareto chart of the flow / valves ( Figure 17). In this chart, the top 10 abnormal valves are dynamically arranged from the most abnormal on the left to the least abnormal on the right.
  • Each Pareto bar also has a reference box indicating the degree of variation of the model abnormality indication that is within normal.
  • the chart in Figure 17 shows that "Valve 10" is substantially outside the normal box but that the others are all behaving normally. The operator would next investigate a plot for "Valve 10" similar to Figure 2 to diagnose the problem with the flow control loop.
  • This engineering unit version of the model can be converted to a standard PCA model format as follows:
  • timers For operator initiated suppression, there are two timers, which determine when the suppression is over. One timer verifies that the suppressed information has returned to and remains in the normal state. Typical values for this timer are from 15 - 30 minutes. The second timer will reactivate the abnormal event check, regardless of whether it has returned to the normal state. Typical values for this timer are either equivalent to the length of the operator's work shift (8 to 12 hours) or a very large time for semi-permanent suppression.
  • a measurable trigger is required. This can be an operator setpoint change, a sudden measurement change, or a digital signal. This signal is converted into a timing signal, shown in Figure 20. This timing signal is created from the trigger signal using the following equations:
  • timing signal As long as the timing signal is above a threshold (shown as .05 in Figure 20), the event remains suppressed.
  • the developer sets the length of the suppression by changing the filter time constant, T f . Although a simple timer could also be used for this function, this timing signal will account for trigger signals of different sizes, creating longer suppressions for large changes and shorter suppressions for smaller changes.
  • Figure 21 shows the event suppression and the operator suppression disabling predefined sets of inputs in the PCA model.
  • the set of inputs to be automatically suppressed is determined from the on-line model performance. Whenever the PCA model gives an indication that the operator does not want to see, this indication can be traced to a small number of individual contributions to the Sum of Error Square index. To suppress these individual contributions, the calculation of this index is modified as follows:
  • the contribution weights are set to zero for each of the inputs that are to be suppressed.
  • the contribution weight is gradually returned to a value of 1.
  • the model indices can be segregated into groupings that better match the operators' view of the process and can improve the sensitivity of the index to an abnormal event.
  • these groupings are based around smaller sub-units of equipment (e.g. reboiler section of a tower), or are sub-groupings, which are relevant to the function of the equipment (e.g. product quality).
  • each principle component can be subdivided to match the equipment groupings and an index analogous to the Hotelling T 2 index can be created for each subgroup.
  • the thresholds for these indices are calculated by running the testing data through the models and setting the sensitivity of the thresholds based on their performance on the test data. [00270] These new indices are interpreted for the operator in the identical manner that a normal PCA model is handled. Pareto charts based on the original inputs are shown for the largest contributors to the sum of error square index, and the largest contributors to the largest P in the T 2 calculation.
  • Inputs will appear in several PCA models so that all interactions affecting the model are encompassed within the model. This can cause multiple indications to the operator when these inputs are the major contributors to the sum of error squared index.
  • any input which appears in multiple PCA models, is assigned one of those PCA models as its primary model.
  • the contribution weight in Equation 29 for the primary PCA model will remain at one while for the non-primary PCA models, it is set to zero.
  • the primary objectives of the operator interface are to:
  • Figure 22 shows how these design objectives are expressed in the primary interfaces used by the operator.
  • the final output from a fuzzy Petri net is a normality trend as is shown in Figure 4.
  • This trend represents the model index that indicates the greatest likelihood of abnormality as defined in the fuzzy discriminate function.
  • the number of trends shown in the summary is flexible and decided in discussions with the operators.
  • On this trend are two reference lines for the operator to help signal when they should take action, a yellow line typically set at a value of 0.6 and a red line typically set at a value of 0.9. These lines provide guidance to the operator as to when he is expected to take action.
  • the green triangle in Figure 4 will turn yellow and when the trend crosses the red line, the green triangle will turn red.
  • the triangle also has the function that it will take the operator to the display associated with the model giving the most abnormal indication.
  • the model is a PCA model or it is part of an equipment group (e.g. all control valves)
  • selecting the green triangle will create a Pareto chart.
  • a PCA model of the dozen largest contributors to the model index, this will indicate the most abnormal (on the left) to the least abnormal (on the right)
  • the key abnormal event indicators will be among the first 2 or 3 measurements.
  • the Pareto chart includes a red box around each bar to provide the operator with a reference as to how unusual the measurement can be before it is regarded as an indication of abnormality.
  • valve models There are a total of 20 valve models developed for the AED PP application. All the valve models have bias-updating implemented. The flow is compensated for the Delta Pressure in this manner:
  • RX1 C2 Feed 165 60 0.1
  • CM Controller Monitor
  • SC Sensor Check
  • the SC checks the relationship between sensors for violation of the correlation rule limits.
  • CM and SC monitors are implemented for the below critical instruments:
  • the PoIyS Cat heuristic model focuses on the detection of catalyst plugging problem in the catalyst area by checking whether the following variables violate rule limits:
  • the 801 Granule, 831 Granule and Finishing 4 Area heuristic models focus on the detection of plugging problems in the three subjected granule areas by checking whether the following variables in each area violate the rule limits:

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Polymerisation Methods In General (AREA)

Abstract

L'invention concerne un procédé et un système permettant la détection d'un événement anormal dans les unités de traitement d'une installation de transformation de polymères. Ce procédé consiste à comparer le fonctionnement des unités de traitement à des modèle statistiques, des modèles d'étude ou des modèles heuristiques. Les modèles statistiques sont mis au point par analyse en composantes principales du fonctionnement normal de ces unités. Les modèles d'étude sont fondés en outre sur une analyse de corrélation entre variables, ou sur de simples calculs d'étude. Si la différence entre le fonctionnement d'une unité de traitement et le résultat du modèle normal indique un état anormal, la cause de cet état anormal est identifiée et rectifiée.
PCT/US2007/007019 2006-03-21 2007-03-20 Application de la technologie de détection d'événements anormaux à la transformation des polymères WO2007109320A2 (fr)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP07753629A EP2013814A4 (fr) 2006-03-21 2007-03-20 Application de la technologie de détection d'événements anormaux à la transformation des polymères
JP2009501541A JP2009536971A (ja) 2006-03-21 2007-03-20 異常事象検出（ａｅｄ）技術のポリマープロセスへの適用
CA2646327A CA2646327C (fr) 2006-03-21 2007-03-20 Application de la technologie de detection d'evenements anormaux a la transformation des polymeres

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US78449806P 2006-03-21 2006-03-21
US60/784,498 2006-03-21
US11/725,227 2007-03-16
US11/725,227 US7761172B2 (en) 2006-03-21 2007-03-16 Application of abnormal event detection (AED) technology to polymers

Publications (2)

Publication Number Publication Date
WO2007109320A2 true WO2007109320A2 (fr) 2007-09-27
WO2007109320A3 WO2007109320A3 (fr) 2009-04-02

Family

ID=38523086

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2007/007019 WO2007109320A2 (fr) 2006-03-21 2007-03-20 Application de la technologie de détection d'événements anormaux à la transformation des polymères

Country Status (5)

Country Link
US (1) US7761172B2 (fr)
EP (1) EP2013814A4 (fr)
JP (1) JP2009536971A (fr)
CA (1) CA2646327C (fr)
WO (1) WO2007109320A2 (fr)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103838209A (zh) * 2013-12-09 2014-06-04 浙江大学 丙烯聚合生产过程自适应最优预报系统和方法
CN103838958A (zh) * 2013-12-09 2014-06-04 浙江大学 模糊智能最优丙烯聚合生产过程最优软测量仪表和方法
WO2018226436A1 (fr) * 2017-06-07 2018-12-13 Honeywell International Inc. Système et procédé de journalisation automatique d'événements dans un système de commande et d'automatisation de processus industriel à l'aide d'une analyse de point de changement
CN115047839A (zh) * 2022-08-17 2022-09-13 北京化工大学 一种甲醇制烯烃工业过程的故障监测方法和系统

Families Citing this family (39)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4097485B2 (ja) * 2002-08-28 2008-06-11 独立行政法人科学技術振興機構 酸化還元酵素と基質との反応中間体を捕捉する方法
US7644624B2 (en) * 2004-06-04 2010-01-12 The Board Of Trustees Of The University Of Illinois Artificial lateral line
US7567887B2 (en) * 2004-09-10 2009-07-28 Exxonmobil Research And Engineering Company Application of abnormal event detection technology to fluidized catalytic cracking unit
US7496798B2 (en) * 2006-02-14 2009-02-24 Jaw Link Data-centric monitoring method
US7720641B2 (en) * 2006-04-21 2010-05-18 Exxonmobil Research And Engineering Company Application of abnormal event detection technology to delayed coking unit
US7912676B2 (en) 2006-07-25 2011-03-22 Fisher-Rosemount Systems, Inc. Method and system for detecting abnormal operation in a process plant
US7657399B2 (en) * 2006-07-25 2010-02-02 Fisher-Rosemount Systems, Inc. Methods and systems for detecting deviation of a process variable from expected values
US8145358B2 (en) 2006-07-25 2012-03-27 Fisher-Rosemount Systems, Inc. Method and system for detecting abnormal operation of a level regulatory control loop
US8606544B2 (en) * 2006-07-25 2013-12-10 Fisher-Rosemount Systems, Inc. Methods and systems for detecting deviation of a process variable from expected values
CN101535909B (zh) * 2006-09-28 2012-08-29 费舍-柔斯芒特系统股份有限公司 热交换器中的异常情况预防
US8032340B2 (en) * 2007-01-04 2011-10-04 Fisher-Rosemount Systems, Inc. Method and system for modeling a process variable in a process plant
US8032341B2 (en) 2007-01-04 2011-10-04 Fisher-Rosemount Systems, Inc. Modeling a process using a composite model comprising a plurality of regression models
US7412356B1 (en) * 2007-01-30 2008-08-12 Lawrence Livermore National Security, Llc Detection and quantification system for monitoring instruments
US7827006B2 (en) * 2007-01-31 2010-11-02 Fisher-Rosemount Systems, Inc. Heat exchanger fouling detection
EP2179338A1 (fr) * 2007-08-14 2010-04-28 Shell Internationale Research Maatschappij B.V. Système et procédés pour la surveillance en ligne continue d'une usine chimique ou d'une raffinerie
US7958065B2 (en) * 2008-03-18 2011-06-07 International Business Machines Corporation Resilient classifier for rule-based system
US8140300B2 (en) * 2008-05-15 2012-03-20 Becton, Dickinson And Company High throughput flow cytometer operation with data quality assessment and control
AT507019B1 (de) * 2008-07-04 2011-03-15 Siemens Vai Metals Tech Gmbh Verfahren zur überwachung einer industrieanlage
US8090676B2 (en) * 2008-09-11 2012-01-03 Honeywell International Inc. Systems and methods for real time classification and performance monitoring of batch processes
WO2010036568A1 (fr) * 2008-09-24 2010-04-01 Huntsman Petrochemical Llc Régulation de la température d'un réacteur à l’aide d’une distribution de probabilités
US8326789B2 (en) * 2009-08-20 2012-12-04 Uop Llc Expert system integrated with remote performance management
US8862250B2 (en) * 2010-05-07 2014-10-14 Exxonmobil Research And Engineering Company Integrated expert system for identifying abnormal events in an industrial plant
US9342072B2 (en) * 2010-09-24 2016-05-17 Fisher-Rosemount Systems, Inc. Methods and apparatus to display process control device information
CN103261241B (zh) 2010-12-22 2016-05-11 巴塞尔聚烯烃股份有限公司 监测乙烯或乙烯与共聚单体在管状反应器中在高压下的聚合的方法
CN102169077B (zh) * 2010-12-28 2013-04-17 东北大学 湿式磨矿过程溢流粒度指标混合智能软测量方法
EP2476901A1 (fr) * 2011-01-17 2012-07-18 Siemens Aktiengesellschaft Procédé et appareil de surveillance pour la surveillance automatisée d'une éolienne et procédé de création d'un modèle linéaire
JP5413399B2 (ja) * 2011-04-11 2014-02-12 三菱自動車工業株式会社 車両搭載機器の故障診断装置
US9130825B2 (en) * 2011-12-27 2015-09-08 Tektronix, Inc. Confidence intervals for key performance indicators in communication networks
US10956014B2 (en) * 2013-12-27 2021-03-23 Baker Hughes, A Ge Company, Llc Systems and methods for dynamically grouping data analysis content
WO2015116326A1 (fr) * 2014-01-30 2015-08-06 Exxonmobil Research And Engineering Company Optimisation en temps réel de procédés discontinus
CN105117553A (zh) * 2015-09-06 2015-12-02 长沙有色冶金设计研究院有限公司 一种水力旋流器溢流粒度的软测量方法
GB2545899B (en) * 2015-12-21 2018-07-25 Imperial Innovations Ltd Management of liquid conduit systems
US10505789B2 (en) * 2016-03-28 2019-12-10 TUPL, Inc. Intelligent configuration system for alert and performance monitoring
WO2017204307A1 (fr) * 2016-05-27 2017-11-30 中部電力株式会社 Système d'évaluation de modèle de système, système de gestion de fonctionnement, procédé d'évaluation de modèle de système et programme
US10997135B2 (en) 2016-09-16 2021-05-04 Oracle International Corporation Method and system for performing context-aware prognoses for health analysis of monitored systems
CN108062565B (zh) * 2017-12-12 2021-12-10 重庆科技学院 基于化工te过程的双主元-动态核主元分析故障诊断方法
US11992818B2 (en) * 2019-08-27 2024-05-28 New York University Method and apparatus for the rapid discovery and design of polymerizations
CN114358465B (zh) * 2021-11-19 2024-08-13 国网上海市电力公司 基于模糊Petri网的配电网工程建设成本管控系统
US11815989B2 (en) * 2022-01-20 2023-11-14 Vmware, Inc. Automated methods and systems for identifying problems in data center objects

Family Cites Families (76)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3175968A (en) 1961-06-23 1965-03-30 Phillips Petroleum Co Automatic control and optimization of a fluidized catalytic cracker
JP2672576B2 (ja) 1988-06-16 1997-11-05 株式会社東芝 プラント・機器の診断支援システム
US5351247A (en) 1988-12-30 1994-09-27 Digital Equipment Corporation Adaptive fault identification system
JPH0660826B2 (ja) 1989-02-07 1994-08-10 動力炉・核燃料開発事業団 プラントの異常診断方法
JPH03154847A (ja) 1989-11-13 1991-07-02 Komatsu Ltd 故障診断装置
JPH0632805A (ja) * 1992-07-17 1994-02-08 Asahi Chem Ind Co Ltd 連続重合プロセスの非定常運転時の制御方法
US5465321A (en) 1993-04-07 1995-11-07 The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration Hidden markov models for fault detection in dynamic systems
JP3147586B2 (ja) * 1993-05-21 2001-03-19 株式会社日立製作所 プラントの監視診断方法
JPH07126303A (ja) * 1993-11-05 1995-05-16 Mitsubishi Chem Corp ポリオレフィン製造プロセスの異常判定方法及びこれを用いた運転支援装置
SE9304246L (sv) 1993-12-22 1995-06-23 Asea Brown Boveri Förfarande vid övervakning av multivariata processer
US5457625A (en) 1994-04-13 1995-10-10 The M. W. Kellogg Company Maximizing process production rates using permanent constraints
US5817958A (en) * 1994-05-20 1998-10-06 Hitachi, Ltd. Plant monitoring and diagnosing method and system, as well as plant equipped with the system
US5539877A (en) 1994-06-27 1996-07-23 International Business Machine Corporation Problem determination method for local area network systems
US6907383B2 (en) 1996-03-28 2005-06-14 Rosemount Inc. Flow diagnostic system
US7085610B2 (en) 1996-03-28 2006-08-01 Fisher-Rosemount Systems, Inc. Root cause diagnostics
US5859964A (en) 1996-10-25 1999-01-12 Advanced Micro Devices, Inc. System and method for performing real time data acquisition, process modeling and fault detection of wafer fabrication processes
JPH10143343A (ja) 1996-11-07 1998-05-29 Fuji Electric Co Ltd 連想型プラント異常診断装置
US5949677A (en) 1997-01-09 1999-09-07 Honeywell Inc. Control system utilizing fault detection
US5950147A (en) 1997-06-05 1999-09-07 Caterpillar Inc. Method and apparatus for predicting a fault condition
US6115656A (en) 1997-06-17 2000-09-05 Mcdonnell Douglas Corporation Fault recording and reporting method
JP2002521201A (ja) 1998-07-21 2002-07-16 ドファスコ インコーポレイテッド 連続鋳造機の動作を監視して切迫したブレークアウトの発生を検出する多変量（ｍｕｌｔｉｖａｒｉａｔｅ）統計的モデルベースのシステム
FI982262A0 (fi) * 1998-10-19 1998-10-19 Valmet Automation Inc Menetelmä ja laitteisto teollisuusprosessin toiminnan seuraamiseksi
US6505145B1 (en) * 1999-02-22 2003-01-07 Northeast Equipment Inc. Apparatus and method for monitoring and maintaining plant equipment
US6368975B1 (en) 1999-07-07 2002-04-09 Applied Materials, Inc. Method and apparatus for monitoring a process by employing principal component analysis
JP2001060110A (ja) 1999-08-20 2001-03-06 Toshiba Eng Co Ltd プラント異常事象評価装置とその方法、ならびに記憶媒体
US6522978B1 (en) 1999-09-15 2003-02-18 General Electric Company Paper web breakage prediction using principal components analysis and classification and regression trees
US6466877B1 (en) 1999-09-15 2002-10-15 General Electric Company Paper web breakage prediction using principal components analysis and classification and regression trees
US6809837B1 (en) 1999-11-29 2004-10-26 Xerox Corporation On-line model prediction and calibration system for a dynamically varying color reproduction device
US6133132A (en) 2000-01-20 2000-10-17 Advanced Micro Devices, Inc. Method for controlling transistor spacer width
CN1433534A (zh) 2000-01-29 2003-07-30 Abb研究有限公司 求出生产设备效率、故障事件和故障事件原因的系统和方法
US6917845B2 (en) 2000-03-10 2005-07-12 Smiths Detection-Pasadena, Inc. Method for monitoring environmental condition using a mathematical model
US7500143B2 (en) 2000-05-05 2009-03-03 Computer Associates Think, Inc. Systems and methods for managing and analyzing faults in computer networks
GB2362481B (en) 2000-05-09 2004-12-01 Rolls Royce Plc Fault diagnosis
US6917839B2 (en) 2000-06-09 2005-07-12 Intellectual Assets Llc Surveillance system and method having an operating mode partitioned fault classification model
US6636842B1 (en) 2000-07-15 2003-10-21 Intevep, S.A. System and method for controlling an industrial process utilizing process trajectories
US6681344B1 (en) 2000-09-14 2004-01-20 Microsoft Corporation System and method for automatically diagnosing a computer problem
US6978210B1 (en) 2000-10-26 2005-12-20 Conocophillips Company Method for automated management of hydrocarbon gathering systems
US20020077792A1 (en) 2000-10-27 2002-06-20 Panacya, Inc. Early warning in e-service management systems
GB0031564D0 (en) * 2000-12-22 2001-02-07 Borealis Tech Oy Viscosity measurement
US6735541B2 (en) 2001-02-16 2004-05-11 Exxonmobil Research And Engineering Company Process unit monitoring program
US6954713B2 (en) 2001-03-01 2005-10-11 Fisher-Rosemount Systems, Inc. Cavitation detection in a process plant
US7389204B2 (en) 2001-03-01 2008-06-17 Fisher-Rosemount Systems, Inc. Data presentation system for abnormal situation prevention in a process plant
JP4564715B2 (ja) 2001-03-01 2010-10-20 フィッシャー−ローズマウント システムズ， インコーポレイテッド ワークオーダ／パーツオーダの自動的生成および追跡
CA2438903C (fr) 2001-03-08 2008-10-21 California Institute Of Technology Analyse d'exception pour multimissions
US20020183971A1 (en) 2001-04-10 2002-12-05 Wegerich Stephan W. Diagnostic systems and methods for predictive condition monitoring
US7539597B2 (en) 2001-04-10 2009-05-26 Smartsignal Corporation Diagnostic systems and methods for predictive condition monitoring
KR100941558B1 (ko) * 2001-05-29 2010-02-10 웨스팅하우스 일렉트릭 컴퍼니 엘엘씨 복합 플랜트의 안정성 모니터링 디스플레이 시스템
GB2379752A (en) * 2001-06-05 2003-03-19 Abb Ab Root cause analysis under conditions of uncertainty
US7457732B2 (en) 2001-08-17 2008-11-25 General Electric Company System and method for measuring quality of baseline modeling techniques
US6904328B2 (en) * 2001-09-14 2005-06-07 Ibex Process Technology, Inc. Large scale process control by driving factor identification
US6980938B2 (en) 2002-01-10 2005-12-27 Cutler Technology Corporation Method for removal of PID dynamics from MPC models
US7096074B2 (en) * 2002-05-30 2006-08-22 Insyst Ltd. Methods and apparatus for early fault detection and alert generation in a process
US6897071B2 (en) 2002-08-13 2005-05-24 Saudi Arabian Oil Company Topological near infrared analysis modeling of petroleum refinery products
US6904386B2 (en) 2002-10-07 2005-06-07 Honeywell International Inc. Control system and method for detecting plugging in differential pressure cells
US7150048B2 (en) 2002-12-18 2006-12-19 Buckman Robert F Method and apparatus for body impact protection
US6993407B2 (en) * 2003-10-02 2006-01-31 Taiwan Semiconductor Manufacturing Company Method and system for analyzing semiconductor fabrication
US7447609B2 (en) 2003-12-31 2008-11-04 Honeywell International Inc. Principal component analysis based fault classification
US7096153B2 (en) * 2003-12-31 2006-08-22 Honeywell International Inc. Principal component analysis based fault classification
US7079984B2 (en) 2004-03-03 2006-07-18 Fisher-Rosemount Systems, Inc. Abnormal situation prevention in a process plant
US7729789B2 (en) 2004-05-04 2010-06-01 Fisher-Rosemount Systems, Inc. Process plant monitoring based on multivariate statistical analysis and on-line process simulation
US7536274B2 (en) 2004-05-28 2009-05-19 Fisher-Rosemount Systems, Inc. System and method for detecting an abnormal situation associated with a heater
US6973396B1 (en) 2004-05-28 2005-12-06 General Electric Company Method for developing a unified quality assessment and providing an automated fault diagnostic tool for turbine machine systems and the like
US7660701B2 (en) 2004-06-12 2010-02-09 Fisher-Rosemount Systems, Inc. System and method for detecting an abnormal situation associated with a process gain of a control loop
US7424395B2 (en) * 2004-09-10 2008-09-09 Exxonmobil Research And Engineering Company Application of abnormal event detection technology to olefins recovery trains
US7567887B2 (en) 2004-09-10 2009-07-28 Exxonmobil Research And Engineering Company Application of abnormal event detection technology to fluidized catalytic cracking unit
US20060074598A1 (en) 2004-09-10 2006-04-06 Emigholz Kenneth F Application of abnormal event detection technology to hydrocracking units
US7349746B2 (en) 2004-09-10 2008-03-25 Exxonmobil Research And Engineering Company System and method for abnormal event detection in the operation of continuous industrial processes
US7181654B2 (en) 2004-09-17 2007-02-20 Fisher-Rosemount Systems, Inc. System and method for detecting an abnormal situation associated with a reactor
CN101305327A (zh) 2005-10-14 2008-11-12 费舍-柔斯芒特系统股份有限公司 与多元统计分析一起用于过程中的故障检测和隔离及异常情况预防的统计特征
ATE546794T1 (de) 2005-10-18 2012-03-15 Honeywell Int Inc System, verfahren und computerprogramm zur frühen ereigniserkennung
US20070088448A1 (en) 2005-10-19 2007-04-19 Honeywell International Inc. Predictive correlation model system
US7243048B2 (en) 2005-11-28 2007-07-10 Honeywell International, Inc. Fault detection system and method using multiway principal component analysis
US7533070B2 (en) * 2006-05-30 2009-05-12 Honeywell International Inc. Automatic fault classification for model-based process monitoring
EP1914638A1 (fr) 2006-10-18 2008-04-23 Bp Oil International Limited Détection d'alarmes par analyse en composantes principales
US8285513B2 (en) 2007-02-27 2012-10-09 Exxonmobil Research And Engineering Company Method and system of using inferential measurements for abnormal event detection in continuous industrial processes
EP2179338A1 (fr) 2007-08-14 2010-04-28 Shell Internationale Research Maatschappij B.V. Système et procédés pour la surveillance en ligne continue d'une usine chimique ou d'une raffinerie

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of EP2013814A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103838209A (zh) * 2013-12-09 2014-06-04 浙江大学 丙烯聚合生产过程自适应最优预报系统和方法
CN103838958A (zh) * 2013-12-09 2014-06-04 浙江大学 模糊智能最优丙烯聚合生产过程最优软测量仪表和方法
WO2018226436A1 (fr) * 2017-06-07 2018-12-13 Honeywell International Inc. Système et procédé de journalisation automatique d'événements dans un système de commande et d'automatisation de processus industriel à l'aide d'une analyse de point de changement
CN115047839A (zh) * 2022-08-17 2022-09-13 北京化工大学 一种甲醇制烯烃工业过程的故障监测方法和系统

Also Published As

Publication number Publication date
CA2646327A1 (fr) 2007-09-27
EP2013814A4 (fr) 2011-04-27
US7761172B2 (en) 2010-07-20
CA2646327C (fr) 2013-12-24
EP2013814A2 (fr) 2009-01-14
JP2009536971A (ja) 2009-10-22
US20080097637A1 (en) 2008-04-24
WO2007109320A3 (fr) 2009-04-02

Similar Documents

Publication Publication Date Title
CA2646327C (fr) Application de la technologie de detection d'evenements anormaux a la transformation des polymeres
CA2578614C (fr) Application d'une technologie de detection d'evenements anormaux dans des unites d'hydrocraquage
CA2578612C (fr) Systeme et procede de detection d'evenements anormaux dans le fonctionnement de processus industriels continus
CA2649863C (fr) Application d'un procede de detection d'evenement anormal a une unite de cokefaction differee
CA2579658C (fr) Application de technologie de detection d'evenement anormal a des trains de recuperation d'olefines
CA2578520C (fr) Application de la technologie de detection d'evenement anormal a une unite de craquage catalytique fluidisee
Patil et al. Prediction and Prognosis of Incipient Off-Spec Events in Diacetone Alcohol Production Process using Hierarchical Process Monitoring

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 07753629

Country of ref document: EP

Kind code of ref document: A2

WWE Wipo information: entry into national phase

Ref document number: 2646327

Country of ref document: CA

WWE Wipo information: entry into national phase

Ref document number: 2009501541

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2007753629

Country of ref document: EP